Difference between revisions of "Unit of Observation"

Jump to: navigation, search
Line 1: Line 1:
<onlyinclude>The unit of observation is the “who” or “what” about which survey data is collected and analysis is focused. Common examples include individual, household, or community. Clearly identifying your unit of observation in datasets and project folders will lead to a more efficient workflow and a more accurate analysis. 
The unit of observation is the unit at or for which data is collected. Common examples include individual, household, community, or school. Clearly identifying the unit of observation is important for a logical [[Questionnaire Design | survey design]], organized data collection, a sound [[DataWork Folder | data folder]] set-up, and an unbiased [[Data Analysis | analysis]]. This page discusses the unit of observation in the context of surveys and datasets and explains how to confirm the unit of observation for a given dataset.  
</onlyinclude>
 
== Read First ==
== Read First ==
*The unit of observation refers to the category, type, or classification of data -- not to specific parties. For example, while student and school are units of observation, “Ali Jones” or “Cedar Elementary School” are not units of observation but rather observations.
* When working with a dataset that you have not created yourself, identifying the unit of observation is the first step to understanding the data.
*Mistakes related to unit of observation introduce bias into analyses. Always double check the unit of observation before working with data.
*Mistakes related to unit of observation introduce bias into analyses. Always double check the unit of observation before working with data.


==Definition==
==Unit of Observation in Surveys==


The unit of observation is the “who” or “what” about which survey data is collected and analysis is focused. Common examples include individual, household, or community. Note that the unit of observation refers to the category, type, or classification of data -- not to specific parties. For example, while student and school are units of observation, “Ali Jones” or “Cedar Elementary School” are not. 
In a survey, the unit of observation describes the unit at or for which survey data is collected. Many times, the unit of observation in a survey is the type of respondent. However, sometimes a respondent provides answers about a larger entity, which is the unit of observation. For example, if school principals are the survey respondents but they provide answers about their schools, the unit of observation is school. If mothers are the survey respondents but they provide answers about their households, the unit of observation is household. However, if school principals are the survey respondents and they provide answers about themselves, then the unit of observation is principal. Similarly, if mothers are the survey respondents and they provide answers about themselves, the unit of observation is mother. Identifying the unit of observation early in the study design is critical for designing a high-quality survey and effectively planning [[Primary Data Collection | primary data collection]].


==Confirming the Unit of Observation==
==Unit of Observation in Datasets==


Just as distance data does not make sense until we know whether its unit is miles or kilometers, survey data and any resulting analyses do not make sense until we know the unit of observation. In many cases, there is seemingly little risk for confusion in terms of unit of observation. We often have a good intuition for the unit of observation at the first glance of a dataset or a file name. However, always test that your assumption is correct: errors due to an unclear understanding of unit of observation are more common than one might imagine. When working with a dataset that you have not created yourself, start by clearly identifying the unit of observation. The most obvious way to do so is by asking the person from whom you received the dataset.
When working with a dataset that you have not created yourself, always start by identifying the unit of observation. In many cases, there is seemingly little risk for confusion in terms of unit of observation. We often have a good intuition for the unit of observation at the first glance of a dataset or a file name. However, always test that your assumption is correct: errors due to an unclear understanding of unit of observation are more common than one might imagine. Consider, for example, monitoring data whose unit of observation is “packages distributed to households.” However, since most households in the dataset only received one package, one could easily confuse the unit of observation to be “household.” Clarifying and confirming the unit of confirmation before beginning to work with a dataset avoids biased [[Data Analysis | analysis]] and makes the way for a correct interpretation of regression and analysis results.  


Consider, however, that you have a dataset for which you do not know the unit of observation and you cannot reach the person from whom you received the dataset. You believe that the unit of observation is household. To confirm, open up the dataset, look for a household ID variable and test if it is [[ID Variable Properties|uniquely and fully identifying]] the dataset. If this is the case, then you are done. However, if you do not find such variable, search for other information that uniquely and fully identifies the dataset. In this case, for example, look for variables with information of household head name. Test if this variable uniquely identifies all observations. Names are often not unique across a country, so you might have to add region name and village name to the test. Once you have found the information that uniquely and fully identifies the dataset, make sure you create an appropriate [[ID Variable Properties|ID variable]] accordingly if it does not yet exist.  
Note that a dataset is always incorrectly constructed if it has more than one unit of observation. Even if the two units of observation have the same variables, it is incorrect, bad practice, and a huge source of error if they are included in the same dataset. All such datasets should be separated into two datasets.


Note that a dataset is always incorrectly constructed if it has more than one unit of observation. Even if the two units of observation have the same variables, it is incorrect, bad practice, and a huge source of error if they were included in the same dataset. All such datasets should be separated into two datasets.
===Confirming Unit of Observation===


==Applications==
The most obvious way to confirm the unit of observation in a new dataset is by asking the person from whom you received the dataset. If you can’t do this for whatever reason, begin by inferring the unit of observation. Imagine you believe the unit of observation is household. Then, open up the dataset, look for a household ID variable and test if it is [[ID Variable Properties|uniquely and fully identifying]]. If it is, then you are done. If not, search for other information that uniquely and fully identifies the dataset. In this case, for example, look for variables with information of household head name. Test if this variable uniquely identifies all observations. Names are often not unique across a country, so you might have to add region name and village name to the test. Once you have found the information that uniquely and fully identifies the dataset, make sure you create an appropriate [[ID Variable Properties|ID variable]] accordingly if it does not yet exist.  
The examples below all have many similarities to how unit of observation is used in the context of a dataset. They are included to give further explanation to the concept or highlight small differences in usage.
 
===Regressions===
In a regression, N (or the number of observations) represents the unit of observation. A correct interpretation of the regression depends on a clear understanding of the unit of observation. In most cases this is trivial, but not always. Consider, for example, monitoring data that is believed to have the unit of observation "households," though its true unit of observation is "packages distributed to households." Since the vast majority of households only received one package each, it is easy yet problematic to make this mistake.
 
Note that some regressions collapse your dataset, so the unit of observation in the regression is different from the unit of observation in your dataset. This is one example when unit of observation cannot described as a row in a dataset.
 
===Surveys===
The concept of unit of observation can also be used to describe for example surveys. The unit of observation in a survey is the type of respondent. For example, household, company, school etc. In the cases of company and school the respondent is a person, for example the CEO or the principal, but they provide answers about the company or the school. If they would be asked questions about themselves, then the unit of observation would be CEOs and principals.


== Back to Parent ==
== Back to Parent ==
Line 31: Line 24:


== Additional Resources ==
== Additional Resources ==
Please add here related articles, including a brief description and link.  
*In [https://www.bmj.com/content/bmj/348/bmj.g3840.full.pdf Unit of observation versus unit of analysis], Philip Sedgwick explains that “the unit of observation, sometimes referred to as the unit of measurement, is defined statistically as the “who” or “what” for which data are measured or collected. The unit of analysis is defined statistically as the “who” or “what” for which information is analysed and conclusions are made.
 
--


[[Category: Data Management ]]
[[Category: Data Management ]]

Revision as of 15:03, 21 May 2019

The unit of observation is the unit at or for which data is collected. Common examples include individual, household, community, or school. Clearly identifying the unit of observation is important for a logical survey design, organized data collection, a sound data folder set-up, and an unbiased analysis. This page discusses the unit of observation in the context of surveys and datasets and explains how to confirm the unit of observation for a given dataset.

Read First

  • The unit of observation refers to the category, type, or classification of data -- not to specific parties. For example, while student and school are units of observation, “Ali Jones” or “Cedar Elementary School” are not units of observation but rather observations.
  • When working with a dataset that you have not created yourself, identifying the unit of observation is the first step to understanding the data.
  • Mistakes related to unit of observation introduce bias into analyses. Always double check the unit of observation before working with data.

Unit of Observation in Surveys

In a survey, the unit of observation describes the unit at or for which survey data is collected. Many times, the unit of observation in a survey is the type of respondent. However, sometimes a respondent provides answers about a larger entity, which is the unit of observation. For example, if school principals are the survey respondents but they provide answers about their schools, the unit of observation is school. If mothers are the survey respondents but they provide answers about their households, the unit of observation is household. However, if school principals are the survey respondents and they provide answers about themselves, then the unit of observation is principal. Similarly, if mothers are the survey respondents and they provide answers about themselves, the unit of observation is mother. Identifying the unit of observation early in the study design is critical for designing a high-quality survey and effectively planning primary data collection.

Unit of Observation in Datasets

When working with a dataset that you have not created yourself, always start by identifying the unit of observation. In many cases, there is seemingly little risk for confusion in terms of unit of observation. We often have a good intuition for the unit of observation at the first glance of a dataset or a file name. However, always test that your assumption is correct: errors due to an unclear understanding of unit of observation are more common than one might imagine. Consider, for example, monitoring data whose unit of observation is “packages distributed to households.” However, since most households in the dataset only received one package, one could easily confuse the unit of observation to be “household.” Clarifying and confirming the unit of confirmation before beginning to work with a dataset avoids biased analysis and makes the way for a correct interpretation of regression and analysis results.

Note that a dataset is always incorrectly constructed if it has more than one unit of observation. Even if the two units of observation have the same variables, it is incorrect, bad practice, and a huge source of error if they are included in the same dataset. All such datasets should be separated into two datasets.

Confirming Unit of Observation

The most obvious way to confirm the unit of observation in a new dataset is by asking the person from whom you received the dataset. If you can’t do this for whatever reason, begin by inferring the unit of observation. Imagine you believe the unit of observation is household. Then, open up the dataset, look for a household ID variable and test if it is uniquely and fully identifying. If it is, then you are done. If not, search for other information that uniquely and fully identifies the dataset. In this case, for example, look for variables with information of household head name. Test if this variable uniquely identifies all observations. Names are often not unique across a country, so you might have to add region name and village name to the test. Once you have found the information that uniquely and fully identifies the dataset, make sure you create an appropriate ID variable accordingly if it does not yet exist.

Back to Parent

This article is part of the topic Data Management

Additional Resources

  • In Unit of observation versus unit of analysis, Philip Sedgwick explains that “the unit of observation, sometimes referred to as the unit of measurement, is defined statistically as the “who” or “what” for which data are measured or collected. The unit of analysis is defined statistically as the “who” or “what” for which information is analysed and conclusions are made.”

--